return dentry_hashtable + hash_32(hash, d_hash_shift);
}
+#define IN_LOOKUP_SHIFT 10
+static struct hlist_bl_head in_lookup_hashtable[1 << IN_LOOKUP_SHIFT];
+
+static inline struct hlist_bl_head *in_lookup_hash(const struct dentry *parent,
+ unsigned int hash)
+{
+ hash += (unsigned long) parent / L1_CACHE_BYTES;
+ return in_lookup_hashtable + hash_32(hash, IN_LOOKUP_SHIFT);
+}
+
+
/* Statistics gathering. */
struct dentry_stat_t dentry_stat = {
.age_limit = 45,
/* Slow case: now with the dentry lock held */
rcu_read_unlock();
+ WARN_ON(d_in_lookup(dentry));
+
/* Unreachable? Get rid of it */
if (unlikely(d_unhashed(dentry)))
goto kill_it;
* be overwriting an internal NUL character
*/
dentry->d_iname[DNAME_INLINE_LEN-1] = 0;
- if (name->len > DNAME_INLINE_LEN-1) {
+ if (unlikely(!name)) {
+ static const struct qstr anon = QSTR_INIT("/", 1);
+ name = &anon;
+ dname = dentry->d_iname;
+ } else if (name->len > DNAME_INLINE_LEN-1) {
size_t size = offsetof(struct external_name, name[1]);
struct external_name *p = kmalloc(size + name->len,
GFP_KERNEL_ACCOUNT);
DCACHE_OP_REVALIDATE |
DCACHE_OP_WEAK_REVALIDATE |
DCACHE_OP_DELETE |
- DCACHE_OP_SELECT_INODE));
+ DCACHE_OP_SELECT_INODE |
+ DCACHE_OP_REAL));
dentry->d_op = op;
if (!op)
return;
dentry->d_flags |= DCACHE_OP_PRUNE;
if (op->d_select_inode)
dentry->d_flags |= DCACHE_OP_SELECT_INODE;
+ if (op->d_real)
+ dentry->d_flags |= DCACHE_OP_REAL;
}
EXPORT_SYMBOL(d_set_d_op);
static void __d_instantiate(struct dentry *dentry, struct inode *inode)
{
unsigned add_flags = d_flags_for_inode(inode);
+ WARN_ON(d_in_lookup(dentry));
spin_lock(&dentry->d_lock);
hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
{
BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
if (inode) {
+ security_d_instantiate(entry, inode);
spin_lock(&inode->i_lock);
__d_instantiate(entry, inode);
spin_unlock(&inode->i_lock);
}
- security_d_instantiate(entry, inode);
}
EXPORT_SYMBOL(d_instantiate);
{
BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
+ security_d_instantiate(entry, inode);
spin_lock(&inode->i_lock);
if (S_ISDIR(inode->i_mode) && !hlist_empty(&inode->i_dentry)) {
spin_unlock(&inode->i_lock);
}
__d_instantiate(entry, inode);
spin_unlock(&inode->i_lock);
- security_d_instantiate(entry, inode);
return 0;
}
struct dentry *res = NULL;
if (root_inode) {
- static const struct qstr name = QSTR_INIT("/", 1);
-
- res = __d_alloc(root_inode->i_sb, &name);
+ res = __d_alloc(root_inode->i_sb, NULL);
if (res)
d_instantiate(res, root_inode);
else
static struct dentry *__d_obtain_alias(struct inode *inode, int disconnected)
{
- static const struct qstr anonstring = QSTR_INIT("/", 1);
struct dentry *tmp;
struct dentry *res;
unsigned add_flags;
if (res)
goto out_iput;
- tmp = __d_alloc(inode->i_sb, &anonstring);
+ tmp = __d_alloc(inode->i_sb, NULL);
if (!tmp) {
res = ERR_PTR(-ENOMEM);
goto out_iput;
}
+ security_d_instantiate(tmp, inode);
spin_lock(&inode->i_lock);
res = __d_find_any_alias(inode);
if (res) {
hlist_bl_unlock(&tmp->d_sb->s_anon);
spin_unlock(&tmp->d_lock);
spin_unlock(&inode->i_lock);
- security_d_instantiate(tmp, inode);
return tmp;
out_iput:
- if (res && !IS_ERR(res))
- security_d_instantiate(res, inode);
iput(inode);
return res;
}
struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
struct qstr *name)
{
- struct dentry *found;
- struct dentry *new;
+ struct dentry *found, *res;
/*
* First check if a dentry matching the name already exists,
* if not go ahead and create it now.
*/
found = d_hash_and_lookup(dentry->d_parent, name);
- if (!found) {
- new = d_alloc(dentry->d_parent, name);
- if (!new) {
- found = ERR_PTR(-ENOMEM);
- } else {
- found = d_splice_alias(inode, new);
- if (found) {
- dput(new);
- return found;
- }
- return new;
+ if (found) {
+ iput(inode);
+ return found;
+ }
+ if (d_in_lookup(dentry)) {
+ found = d_alloc_parallel(dentry->d_parent, name,
+ dentry->d_wait);
+ if (IS_ERR(found) || !d_in_lookup(found)) {
+ iput(inode);
+ return found;
}
+ } else {
+ found = d_alloc(dentry->d_parent, name);
+ if (!found) {
+ iput(inode);
+ return ERR_PTR(-ENOMEM);
+ }
+ }
+ res = d_splice_alias(inode, found);
+ if (res) {
+ dput(found);
+ return res;
}
- iput(inode);
return found;
}
EXPORT_SYMBOL(d_add_ci);
}
EXPORT_SYMBOL(d_rehash);
+static inline unsigned start_dir_add(struct inode *dir)
+{
+
+ for (;;) {
+ unsigned n = dir->i_dir_seq;
+ if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n)
+ return n;
+ cpu_relax();
+ }
+}
+
+static inline void end_dir_add(struct inode *dir, unsigned n)
+{
+ smp_store_release(&dir->i_dir_seq, n + 2);
+}
+
+static void d_wait_lookup(struct dentry *dentry)
+{
+ if (d_in_lookup(dentry)) {
+ DECLARE_WAITQUEUE(wait, current);
+ add_wait_queue(dentry->d_wait, &wait);
+ do {
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ spin_unlock(&dentry->d_lock);
+ schedule();
+ spin_lock(&dentry->d_lock);
+ } while (d_in_lookup(dentry));
+ }
+}
+
+struct dentry *d_alloc_parallel(struct dentry *parent,
+ const struct qstr *name,
+ wait_queue_head_t *wq)
+{
+ unsigned int len = name->len;
+ unsigned int hash = name->hash;
+ const unsigned char *str = name->name;
+ struct hlist_bl_head *b = in_lookup_hash(parent, hash);
+ struct hlist_bl_node *node;
+ struct dentry *new = d_alloc(parent, name);
+ struct dentry *dentry;
+ unsigned seq, r_seq, d_seq;
+
+ if (unlikely(!new))
+ return ERR_PTR(-ENOMEM);
+
+retry:
+ rcu_read_lock();
+ seq = smp_load_acquire(&parent->d_inode->i_dir_seq) & ~1;
+ r_seq = read_seqbegin(&rename_lock);
+ dentry = __d_lookup_rcu(parent, name, &d_seq);
+ if (unlikely(dentry)) {
+ if (!lockref_get_not_dead(&dentry->d_lockref)) {
+ rcu_read_unlock();
+ goto retry;
+ }
+ if (read_seqcount_retry(&dentry->d_seq, d_seq)) {
+ rcu_read_unlock();
+ dput(dentry);
+ goto retry;
+ }
+ rcu_read_unlock();
+ dput(new);
+ return dentry;
+ }
+ if (unlikely(read_seqretry(&rename_lock, r_seq))) {
+ rcu_read_unlock();
+ goto retry;
+ }
+ hlist_bl_lock(b);
+ if (unlikely(parent->d_inode->i_dir_seq != seq)) {
+ hlist_bl_unlock(b);
+ rcu_read_unlock();
+ goto retry;
+ }
+ rcu_read_unlock();
+ /*
+ * No changes for the parent since the beginning of d_lookup().
+ * Since all removals from the chain happen with hlist_bl_lock(),
+ * any potential in-lookup matches are going to stay here until
+ * we unlock the chain. All fields are stable in everything
+ * we encounter.
+ */
+ hlist_bl_for_each_entry(dentry, node, b, d_u.d_in_lookup_hash) {
+ if (dentry->d_name.hash != hash)
+ continue;
+ if (dentry->d_parent != parent)
+ continue;
+ if (d_unhashed(dentry))
+ continue;
+ if (parent->d_flags & DCACHE_OP_COMPARE) {
+ int tlen = dentry->d_name.len;
+ const char *tname = dentry->d_name.name;
+ if (parent->d_op->d_compare(parent, dentry, tlen, tname, name))
+ continue;
+ } else {
+ if (dentry->d_name.len != len)
+ continue;
+ if (dentry_cmp(dentry, str, len))
+ continue;
+ }
+ dget(dentry);
+ hlist_bl_unlock(b);
+ /* somebody is doing lookup for it right now; wait for it */
+ spin_lock(&dentry->d_lock);
+ d_wait_lookup(dentry);
+ /*
+ * it's not in-lookup anymore; in principle we should repeat
+ * everything from dcache lookup, but it's likely to be what
+ * d_lookup() would've found anyway. If it is, just return it;
+ * otherwise we really have to repeat the whole thing.
+ */
+ if (unlikely(dentry->d_name.hash != hash))
+ goto mismatch;
+ if (unlikely(dentry->d_parent != parent))
+ goto mismatch;
+ if (unlikely(d_unhashed(dentry)))
+ goto mismatch;
+ if (parent->d_flags & DCACHE_OP_COMPARE) {
+ int tlen = dentry->d_name.len;
+ const char *tname = dentry->d_name.name;
+ if (parent->d_op->d_compare(parent, dentry, tlen, tname, name))
+ goto mismatch;
+ } else {
+ if (unlikely(dentry->d_name.len != len))
+ goto mismatch;
+ if (unlikely(dentry_cmp(dentry, str, len)))
+ goto mismatch;
+ }
+ /* OK, it *is* a hashed match; return it */
+ spin_unlock(&dentry->d_lock);
+ dput(new);
+ return dentry;
+ }
+ /* we can't take ->d_lock here; it's OK, though. */
+ new->d_flags |= DCACHE_PAR_LOOKUP;
+ new->d_wait = wq;
+ hlist_bl_add_head_rcu(&new->d_u.d_in_lookup_hash, b);
+ hlist_bl_unlock(b);
+ return new;
+mismatch:
+ spin_unlock(&dentry->d_lock);
+ dput(dentry);
+ goto retry;
+}
+EXPORT_SYMBOL(d_alloc_parallel);
+
+void __d_lookup_done(struct dentry *dentry)
+{
+ struct hlist_bl_head *b = in_lookup_hash(dentry->d_parent,
+ dentry->d_name.hash);
+ hlist_bl_lock(b);
+ dentry->d_flags &= ~DCACHE_PAR_LOOKUP;
+ __hlist_bl_del(&dentry->d_u.d_in_lookup_hash);
+ wake_up_all(dentry->d_wait);
+ dentry->d_wait = NULL;
+ hlist_bl_unlock(b);
+ INIT_HLIST_NODE(&dentry->d_u.d_alias);
+ INIT_LIST_HEAD(&dentry->d_lru);
+}
+EXPORT_SYMBOL(__d_lookup_done);
/* inode->i_lock held if inode is non-NULL */
static inline void __d_add(struct dentry *dentry, struct inode *inode)
{
+ struct inode *dir = NULL;
+ unsigned n;
+ spin_lock(&dentry->d_lock);
+ if (unlikely(d_in_lookup(dentry))) {
+ dir = dentry->d_parent->d_inode;
+ n = start_dir_add(dir);
+ __d_lookup_done(dentry);
+ }
if (inode) {
- __d_instantiate(dentry, inode);
- spin_unlock(&inode->i_lock);
+ unsigned add_flags = d_flags_for_inode(inode);
+ hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
+ raw_write_seqcount_begin(&dentry->d_seq);
+ __d_set_inode_and_type(dentry, inode, add_flags);
+ raw_write_seqcount_end(&dentry->d_seq);
+ __fsnotify_d_instantiate(dentry);
}
- security_d_instantiate(dentry, inode);
- d_rehash(dentry);
+ _d_rehash(dentry);
+ if (dir)
+ end_dir_add(dir, n);
+ spin_unlock(&dentry->d_lock);
+ if (inode)
+ spin_unlock(&inode->i_lock);
}
/**
void d_add(struct dentry *entry, struct inode *inode)
{
- if (inode)
+ if (inode) {
+ security_d_instantiate(entry, inode);
spin_lock(&inode->i_lock);
+ }
__d_add(entry, inode);
}
EXPORT_SYMBOL(d_add);
static void __d_move(struct dentry *dentry, struct dentry *target,
bool exchange)
{
+ struct inode *dir = NULL;
+ unsigned n;
if (!dentry->d_inode)
printk(KERN_WARNING "VFS: moving negative dcache entry\n");
BUG_ON(d_ancestor(target, dentry));
dentry_lock_for_move(dentry, target);
+ if (unlikely(d_in_lookup(target))) {
+ dir = target->d_parent->d_inode;
+ n = start_dir_add(dir);
+ __d_lookup_done(target);
+ }
write_seqcount_begin(&dentry->d_seq);
write_seqcount_begin_nested(&target->d_seq, DENTRY_D_LOCK_NESTED);
write_seqcount_end(&target->d_seq);
write_seqcount_end(&dentry->d_seq);
+ if (dir)
+ end_dir_add(dir, n);
dentry_unlock_for_move(dentry, target);
}
static int __d_unalias(struct inode *inode,
struct dentry *dentry, struct dentry *alias)
{
- struct mutex *m1 = NULL, *m2 = NULL;
+ struct mutex *m1 = NULL;
+ struct rw_semaphore *m2 = NULL;
int ret = -ESTALE;
/* If alias and dentry share a parent, then no extra locks required */
if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex))
goto out_err;
m1 = &dentry->d_sb->s_vfs_rename_mutex;
- if (!inode_trylock(alias->d_parent->d_inode))
+ if (!inode_trylock_shared(alias->d_parent->d_inode))
goto out_err;
- m2 = &alias->d_parent->d_inode->i_mutex;
+ m2 = &alias->d_parent->d_inode->i_rwsem;
out_unalias:
__d_move(alias, dentry, false);
ret = 0;
out_err:
if (m2)
- mutex_unlock(m2);
+ up_read(m2);
if (m1)
mutex_unlock(m1);
return ret;
if (!inode)
goto out;
+ security_d_instantiate(dentry, inode);
spin_lock(&inode->i_lock);
if (S_ISDIR(inode->i_mode)) {
struct dentry *new = __d_find_any_alias(inode);
} else {
__d_move(new, dentry, false);
write_sequnlock(&rename_lock);
- security_d_instantiate(new, inode);
}
iput(inode);
return new;
/**
* ecryptfs_lookup_interpose - Dentry interposition for a lookup
*/
- static int ecryptfs_lookup_interpose(struct dentry *dentry,
- struct dentry *lower_dentry,
- struct inode *dir_inode)
+ static struct dentry *ecryptfs_lookup_interpose(struct dentry *dentry,
+ struct dentry *lower_dentry)
{
struct inode *inode, *lower_inode = d_inode(lower_dentry);
struct ecryptfs_dentry_info *dentry_info;
"to allocate ecryptfs_dentry_info struct\n",
__func__);
dput(lower_dentry);
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
}
lower_mnt = mntget(ecryptfs_dentry_to_lower_mnt(dentry->d_parent));
- fsstack_copy_attr_atime(dir_inode, d_inode(lower_dentry->d_parent));
+ fsstack_copy_attr_atime(d_inode(dentry->d_parent),
+ d_inode(lower_dentry->d_parent));
BUG_ON(!d_count(lower_dentry));
ecryptfs_set_dentry_private(dentry, dentry_info);
if (d_really_is_negative(lower_dentry)) {
/* We want to add because we couldn't find in lower */
d_add(dentry, NULL);
- return 0;
+ return NULL;
}
- inode = __ecryptfs_get_inode(lower_inode, dir_inode->i_sb);
+ inode = __ecryptfs_get_inode(lower_inode, dentry->d_sb);
if (IS_ERR(inode)) {
printk(KERN_ERR "%s: Error interposing; rc = [%ld]\n",
__func__, PTR_ERR(inode));
- return PTR_ERR(inode);
+ return ERR_CAST(inode);
}
if (S_ISREG(inode->i_mode)) {
rc = ecryptfs_i_size_read(dentry, inode);
if (rc) {
make_bad_inode(inode);
- return rc;
+ return ERR_PTR(rc);
}
}
if (inode->i_state & I_NEW)
unlock_new_inode(inode);
- d_add(dentry, inode);
-
- return rc;
+ return d_splice_alias(inode, dentry);
}
/**
unsigned int flags)
{
char *encrypted_and_encoded_name = NULL;
- size_t encrypted_and_encoded_name_size;
- struct ecryptfs_mount_crypt_stat *mount_crypt_stat = NULL;
+ struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
struct dentry *lower_dir_dentry, *lower_dentry;
+ const char *name = ecryptfs_dentry->d_name.name;
+ size_t len = ecryptfs_dentry->d_name.len;
+ struct dentry *res;
int rc = 0;
lower_dir_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry->d_parent);
- lower_dentry = lookup_one_len_unlocked(ecryptfs_dentry->d_name.name,
- lower_dir_dentry,
- ecryptfs_dentry->d_name.len);
- if (IS_ERR(lower_dentry)) {
- rc = PTR_ERR(lower_dentry);
- ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned "
- "[%d] on lower_dentry = [%pd]\n", __func__, rc,
- ecryptfs_dentry);
- goto out;
- }
- if (d_really_is_positive(lower_dentry))
- goto interpose;
+
mount_crypt_stat = &ecryptfs_superblock_to_private(
ecryptfs_dentry->d_sb)->mount_crypt_stat;
- if (!(mount_crypt_stat
- && (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)))
- goto interpose;
- dput(lower_dentry);
- rc = ecryptfs_encrypt_and_encode_filename(
- &encrypted_and_encoded_name, &encrypted_and_encoded_name_size,
- mount_crypt_stat, ecryptfs_dentry->d_name.name,
- ecryptfs_dentry->d_name.len);
- if (rc) {
- printk(KERN_ERR "%s: Error attempting to encrypt and encode "
- "filename; rc = [%d]\n", __func__, rc);
- goto out;
+ if (mount_crypt_stat
+ && (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)) {
+ rc = ecryptfs_encrypt_and_encode_filename(
+ &encrypted_and_encoded_name, &len,
+ mount_crypt_stat, name, len);
+ if (rc) {
+ printk(KERN_ERR "%s: Error attempting to encrypt and encode "
+ "filename; rc = [%d]\n", __func__, rc);
+ return ERR_PTR(rc);
+ }
+ name = encrypted_and_encoded_name;
}
- lower_dentry = lookup_one_len_unlocked(encrypted_and_encoded_name,
- lower_dir_dentry,
- encrypted_and_encoded_name_size);
+
+ lower_dentry = lookup_one_len_unlocked(name, lower_dir_dentry, len);
if (IS_ERR(lower_dentry)) {
- rc = PTR_ERR(lower_dentry);
ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned "
- "[%d] on lower_dentry = [%s]\n", __func__, rc,
- encrypted_and_encoded_name);
- goto out;
+ "[%ld] on lower_dentry = [%s]\n", __func__,
+ PTR_ERR(lower_dentry),
+ name);
+ res = ERR_CAST(lower_dentry);
+ } else {
+ res = ecryptfs_lookup_interpose(ecryptfs_dentry, lower_dentry);
}
- interpose:
- rc = ecryptfs_lookup_interpose(ecryptfs_dentry, lower_dentry,
- ecryptfs_dir_inode);
- out:
kfree(encrypted_and_encoded_name);
- return ERR_PTR(rc);
+ return res;
}
static int ecryptfs_link(struct dentry *old_dentry, struct inode *dir,
} else { /* ia->ia_size < i_size_read(inode) */
/* We're chopping off all the pages down to the page
* in which ia->ia_size is located. Fill in the end of
- * that page from (ia->ia_size & ~PAGE_CACHE_MASK) to
- * PAGE_CACHE_SIZE with zeros. */
- size_t num_zeros = (PAGE_CACHE_SIZE
- - (ia->ia_size & ~PAGE_CACHE_MASK));
+ * that page from (ia->ia_size & ~PAGE_MASK) to
+ * PAGE_SIZE with zeros. */
+ size_t num_zeros = (PAGE_SIZE
+ - (ia->ia_size & ~PAGE_MASK));
if (!(crypt_stat->flags & ECRYPTFS_ENCRYPTED)) {
truncate_setsize(inode, ia->ia_size);
struct ecryptfs_crypt_stat *crypt_stat;
crypt_stat = &ecryptfs_inode_to_private(d_inode(dentry))->crypt_stat;
- if (!(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED))
- ecryptfs_init_crypt_stat(crypt_stat);
+ if (!(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED)) {
+ rc = ecryptfs_init_crypt_stat(crypt_stat);
+ if (rc)
+ return rc;
+ }
inode = d_inode(dentry);
lower_inode = ecryptfs_inode_to_lower(inode);
lower_dentry = ecryptfs_dentry_to_lower(dentry);
}
ssize_t
-ecryptfs_getxattr_lower(struct dentry *lower_dentry, const char *name,
- void *value, size_t size)
+ecryptfs_getxattr_lower(struct dentry *lower_dentry, struct inode *lower_inode,
+ const char *name, void *value, size_t size)
{
int rc = 0;
- if (!d_inode(lower_dentry)->i_op->getxattr) {
+ if (!lower_inode->i_op->getxattr) {
rc = -EOPNOTSUPP;
goto out;
}
- inode_lock(d_inode(lower_dentry));
- rc = d_inode(lower_dentry)->i_op->getxattr(lower_dentry, name, value,
- size);
- inode_unlock(d_inode(lower_dentry));
+ inode_lock(lower_inode);
+ rc = lower_inode->i_op->getxattr(lower_dentry, lower_inode,
+ name, value, size);
+ inode_unlock(lower_inode);
out:
return rc;
}
static ssize_t
-ecryptfs_getxattr(struct dentry *dentry, const char *name, void *value,
- size_t size)
+ecryptfs_getxattr(struct dentry *dentry, struct inode *inode,
+ const char *name, void *value, size_t size)
{
- return ecryptfs_getxattr_lower(ecryptfs_dentry_to_lower(dentry), name,
- value, size);
+ return ecryptfs_getxattr_lower(ecryptfs_dentry_to_lower(dentry),
+ ecryptfs_inode_to_lower(inode),
+ name, value, size);
}
static ssize_t